v0.6.1-beta

[FMCalisto]

v0.6.1-beta - Robust BIRADS Parsing and Multimodal Analysis

This pre-release improves robustness and correctness of BIRADS parsing across multimodal imaging pipelines (MG, US, MRI).

Improvements

• Fixed parsing of float values (e.g., "5.0")
• Fixed handling of multiple annotations per cell ("," and ";" separators)
• Correct extraction of maximum BIRADS per patient
• Improved handling of empty and malformed values
• Stable generation of:
  • MG frequency plots (CCL, CCR, MLOL, MLOR)
  • US side-by-side plots (USL vs USR with image counts)
  • MRI side-by-side plots (MRIL vs MRIR)

Technical Fixes

• Eliminated errors:
  • "invalid literal for int()"
  • "max() arg is an empty sequence"
  • duplicate index issues in pandas
• Improved regex-based parsing
• Added safer numeric extraction logic

Notes

• MRI data may remain sparse depending on dataset completeness
• This is a beta release and not production-ready

Ecosystem

• https://github.com/MIMBCD-UI
• https://github.com/mida-project
• https://github.com/BreastScreening
• https://github.com/BreastScreeningAI

Next Steps

• Zenodo DOI integration
• JSON metadata standardization
• Unit testing for parsing edge cases

---

This discussion was created from the release v0.6.1-beta.